{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/parameter-efficient-image-to-video-transfer","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","arxiv_id":"2206.13559","date":"2022-06-27","proceeding":null,"authors":["Junting Pan","Ziyi Lin","Xiatian Zhu","Jing Shao","Hongsheng Li"],"abstract":"Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine-tuning based task adaptation strategy becomes prohibitively costly in terms of model training and storage. This has led to a new research direction in parameter-efficient transfer learning. However, existing attempts typically focus on downstream tasks from the same modality (e.g., image understanding) of the pre-trained model. This creates a limit because in some specific modalities, (e.g., video understanding) such a strong pre-trained model with sufficient knowledge is less or not available. In this work, we investigate such a novel cross-modality transfer learning setting, namely parameter-efficient image-to-video transfer learning. To solve this problem, we propose a new Spatio-Temporal Adapter (ST-Adapter) for parameter-efficient fine-tuning per video task. With a built-in spatio-temporal reasoning capability in a compact design, ST-Adapter enables a pre-trained image model without temporal knowledge to reason about dynamic video content at a small (~8%) per-task parameter cost, requiring approximately 20 times fewer updated parameters compared to previous work. Extensive experiments on video action recognition tasks show that our ST-Adapter can match or even outperform the strong full fine-tuning strategy and state-of-the-art video models, whilst enjoying the advantage of parameter efficiency. The code and model are available at https://github.com/linziyi96/st-adapter","url_abs":"https://arxiv.org/abs/2206.13559v3","url_pdf":"https://arxiv.org/pdf/2206.13559v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"parameter-efficient-image-to-video-transfer","repo_url":"https://github.com/linziyi96/st-adapter","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ST-Adapter (ViT-L, CLIP)","rank_in_archive_order":37,"of":207,"metrics":{"Acc@1":"87.2","Acc@5":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"ST-Adapter (ViT-L, CLIP)","rank_in_archive_order":24,"of":123,"metrics":{"GFLOPs":"8248","Top-1 Accuracy":"72.3","Top-5 Accuracy":"93.9"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2206.13559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.13559"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/linziyi96/st-adapter","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"157585dc6ae8a498","entry":"crop_boxes","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/transform.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/transform.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"157585dc6ae8a498"}},{"code_sha256_prefix":"e866e1196986f728","entry":"shear_x","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/rand_augment.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/rand_augment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e866e1196986f728"}},{"code_sha256_prefix":"7b2503c99c9447fb","entry":"shear_y","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/rand_augment.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/rand_augment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b2503c99c9447fb"}},{"code_sha256_prefix":"323759f906fbb394","entry":"translate_x_rel","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/rand_augment.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/rand_augment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"323759f906fbb394"}},{"code_sha256_prefix":"547be2babaca4859","entry":"convert_to_one_hot","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/mixup.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/mixup.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"547be2babaca4859"}},{"code_sha256_prefix":"319881416fb3b9dc","entry":"load_model","repo":"linziyi96/st-adapter","repo_kind":"official","path":"utils.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"319881416fb3b9dc"}},{"code_sha256_prefix":"fd3e5fd51b6d7296","entry":"mixup_target","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/mixup.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/mixup.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd3e5fd51b6d7296"}},{"code_sha256_prefix":"830c7d87b9bb8311","entry":"rand_bbox","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/mixup.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/mixup.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"830c7d87b9bb8311"}},{"code_sha256_prefix":"64ce021674e30869","entry":"random_crop","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/transform.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/transform.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64ce021674e30869"}},{"code_sha256_prefix":"472299265598d14e","entry":"random_short_side_scale_jitter","repo":"linziyi96/st-adapter","repo_kind":"official","path":"video_dataset/transform.py","file_url":"https://github.com/linziyi96/st-adapter/blob/HEAD/video_dataset/transform.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"472299265598d14e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}